Amazon has updated the AgentCore Gateway to support automated token exchange between Microsoft Entra ID and protected REST APIs. By leveraging this flow, AI agents can now perform actions in platforms like ServiceNow using the identity and permissions of the end-user rather than acting as a generic service account.
Cartesia has introduced two models for voice applications: Sonic (text-to-speech) and Ink (speech-to-text). Built on State Space Model (SSM) architecture, these models are designed for ultra-low-latency, real-time performance suitable for production voice agents.
Cloudflare has introduced Zero Wire, a public intelligence feed within Cloudflare Radar that consolidates critical vulnerability data. It provides simple, actionable briefings on major Internet-facing security flaws, including suggested next steps for engineering and security teams.
Recent research shows that commercial AI text humanizers, designed to bypass AI detectors, frequently alter or drop essential facts like names, numbers, and dates. Across 11 tested tools, 35-65% of documents containing factual details suffered from errors during the re-writing process.
Research shows that identical persona instructions produce different behavioral outcomes in LLMs when switching from English to Korean. While buyers followed instructions similarly, sellers became significantly more accommodating and polite in Korean, leading to higher agreement rates and lower prices.
Researchers have introduced MEMENTO, a specialized agentic framework built on Qwen3-8B designed to manage long context by compacting history into concise notes. By utilizing fine-tuning on synthetic trajectories followed by reinforcement learning, it achieves high accuracy on book-level tasks while strictly limiting context usage to 20K tokens, even for inputs as large as 2.5 million tokens.
NVIDIA has open-sourced 'NVIDIA Attribution,' a tool designed to correlate logs, metrics, and scheduler states into structured diagnoses for distributed AI training jobs. By identifying root causes and distinguishing them from downstream symptoms (like NCCL errors), it helps infrastructure teams manage large-scale GPU deployments more effectively.
NVIDIA Recovery is a new open-source service built to maintain productive training by automating job-level fault handling across GPU clusters. It replaces manual oversight with a systematic loop that detects errors, identifies causes, and triggers restarts or node exclusions.
The new message threads feature in beta allows developers to keep conversation state on the server. By sending only incremental updates instead of the full history, you can achieve faster response times in complex agentic loops.
NVIDIA has released updated AI Cluster Runtime (AICR) recipes designed to streamline the deployment of Kubernetes on the new Vera Rubin NVL72 hardware. These recipes provide pre-validated configurations for drivers, kernels, and network components, ensuring production-ready clusters from day one.
Amazon introduced a multi-agent system built on Bedrock AgentCore that automates engineering document evaluation and substitution. The architecture combines multimodal retrieval, deterministic Python-based tolerance checking, and hierarchical LLM orchestration.
NVIDIA has introduced Cosmos, a platform offering world foundation models and development tools specifically designed for physical AI applications, such as robotics and autonomous vehicles. The framework includes modular training recipes and NIM microservices for GPU-accelerated inference, enabling the generation of synchronized video and LiDAR observations.
Amazon has published a workflow for using Sequence-Level Knowledge Distillation (SeqKD) to fine-tune smaller models on trajectories generated by frontier models. By using a 'teacher' model to generate successful tool-use trajectories and filtering them with a programmatic scorer, teams can train compact 'student' models that perform complex reasoning at a fraction of the cost.
NVIDIA has released Workload Map, a tool designed to provide a common way for Kubernetes schedulers and platforms to interpret diverse distributed AI workloads. By using declarative YAML definitions, it eliminates the need for developers to build custom parsing adapters for every new framework like JobSet, Ray, or KServe.
Apple researchers have unveiled an online training infrastructure for mobile UI agents that utilizes a two-part architecture to split navigational logic from visual interpretation. By employing step-level feedback provided by an LLM-as-a-Judge and a novel value estimation technique known as GiGPPO, these agents demonstrate significantly better adaptability than static models trained on pre-recorded sequences.
Recent research shows that many attention heads in large language models are redundant and specifically contribute to verbatim memorisation of training data. By selectively pruning these heads at inference time, researchers achieved a 91.5% reduction in memorisation events while simultaneously improving performance on standard benchmarks.
Recent research reveals that language models fail to adapt to evolving user preferences, instead defaulting to 'exploit-first' behavior. While models can identify the correct strategy in multiple-choice scenarios, they show a 35-46% drop in calibration during open-ended generation, persistently over-relying on stale historical data.
A new research paper introduces Mage-VL-Cowork, a 4B parameter computer-use agent that combines GUI interaction with code and terminal execution. By utilizing a new synthetic data framework called Mage-CUA-Forge, the developers reduced per-task training expenditure by 82.6% while reaching 66% on the OSWorld-Verified benchmark.
Researchers introduced CoFiBreak, a reward mechanism for training attacker LLMs that forces a higher diversity of jailbreak strategies. By using a coarse-to-fine reward structure in Group Relative Policy Optimization, the method avoids the typical reinforcement learning collapse where models converge on a narrow set of repetitive prompts.
NVIDIA has released AI Cluster Runtime (AICR) to package Dynamo inference infrastructure into validated recipes. This update simplifies deployment by pinning versions and removing mandatory external dependencies like NATS, while introducing new KV-aware routing paths for Kubernetes.
Amazon Bedrock AgentCore now supports Session endpoints, allowing developers to view and interact with web applications live as an AI coding agent builds them. By routing traffic through an authenticated, isolated microVM session, changes appear in the browser instantly without requiring separate deployments.
Anthropic has announced the deprecation of the fast mode for the Claude Opus 4.8 model. Support for this mode will be completely removed on November 30, 2026, after which requests will result in an error.
NVIDIA has released a new command-line interface for the TensorRT Edge-LLM runtime, allowing developers to quickly prototype and test AI models on the DGX Spark 64GB workstation. The tool chain facilitates local model serving and supports DSpark speculative decoding to boost generation performance on edge-constrained hardware.
Effective automation depends on how your workflows handle API constraints. This guide distinguishes between rate limiting (hard caps leading to 429 errors) and throttling (delaying requests), providing strategies like exponential backoff, jitter, and proactive batching to maintain reliability.